Agent DailyAgent Daily
releaseintermediate

[Release] openai/openai-agents-python v0.10.3: v0.10.3

By seratchgithub
View original on github

OpenAI Agents Python v0.10.3 release includes new features for exposing immutable agent tool invocation metadata on run results and adding RunResult tool_context accessor for agent tools. Performance improvements include using deque for BFS queue and voice task ordering, along with comprehensive documentation updates and test enhancements.

Key Points

  • Expose immutable agent tool invocation metadata on run results for better observability and debugging of tool calls
  • Add RunResult tool_context accessor to enable agent tools to access contextual information during execution
  • Optimize performance by replacing BFS queue implementation with deque and improving voice task ordering
  • Enhance documentation with nest_handoff_history parameter details and reorganized runtime guides for clarity
  • Improve test execution speed using xdist parallelization and deterministic waits for more reliable testing
  • Add MCP (Model Context Protocol) failure handling with tool_call_output_item emission for better error tracking
  • Update security and infrastructure dependencies (setup-uv, actions/stale) to latest versions
  • Maintain multi-language documentation with automated translation updates across all supported languages

Found this useful? Add it to a playbook for a step-by-step implementation guide.

Workflow Diagram

Start Process
Step A
Step B
Step C
Complete
Quality

Concepts

[Release] openai/openai-agents-python v0.10.3: v0.10.3 | Agent Daily